emnlp-experiments
Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill emnlp-experiments --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# EMNLP Experiments Use this while the experimental grid is still cheap to change. EMNLP's reviewing culture was partly built by papers criticizing NLP's own evaluation habits, so the venue audits experiments the way a security reviewer audits inputs: assume the design will be probed for the easiest way to make the headline number lie. ## The five probes reviewers run 1. **Baseline fairness.** Did
What does the emnlp-experiments skill do?
Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill emnlp-experiments --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.